shithub: opus

Info  •  Files  •  Log  •  Branches

Adding option to change frame rate network size

--- a/dnn/training_tf2/dump_lpcnet.py

+++ b/dnn/training_tf2/dump_lpcnet.py

@@ -249,8 +249,9 @@

 with h5py.File(filename, "r") as f:

     units = min(f['model_weights']['gru_a']['gru_a']['recurrent_kernel:0'].shape)

     units2 = min(f['model_weights']['gru_b']['gru_b']['recurrent_kernel:0'].shape)

+    cond_size = min(f['model_weights']['feature_dense1']['feature_dense1']['kernel:0'].shape)

-model, _, _ = lpcnet.new_lpcnet_model(rnn_units1=units, rnn_units2=units2, flag_e2e = flag_e2e)

+model, _, _ = lpcnet.new_lpcnet_model(rnn_units1=units, rnn_units2=units2, flag_e2e = flag_e2e, cond_size=cond_size)

 model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['sparse_categorical_accuracy'])

 #model.summary()

--- a/dnn/training_tf2/lpcnet.py

+++ b/dnn/training_tf2/lpcnet.py

@@ -230,24 +230,24 @@

 constraint = WeightClip(0.992)

-def new_lpcnet_model(rnn_units1=384, rnn_units2=16, nb_used_features=20, batch_size=128, training=False, adaptation=False, quantize=False, flag_e2e = False):

+def new_lpcnet_model(rnn_units1=384, rnn_units2=16, nb_used_features=20, batch_size=128, training=False, adaptation=False, quantize=False, flag_e2e = False, cond_size=128):

     pcm = Input(shape=(None, 3), batch_size=batch_size)

     feat = Input(shape=(None, nb_used_features), batch_size=batch_size)

     pitch = Input(shape=(None, 1), batch_size=batch_size)

-    dec_feat = Input(shape=(None, 128))

+    dec_feat = Input(shape=(None, cond_size))

     dec_state1 = Input(shape=(rnn_units1,))

     dec_state2 = Input(shape=(rnn_units2,))

     padding = 'valid' if training else 'same'

-    fconv1 = Conv1D(128, 3, padding=padding, activation='tanh', name='feature_conv1')

-    fconv2 = Conv1D(128, 3, padding=padding, activation='tanh', name='feature_conv2')

+    fconv1 = Conv1D(cond_size, 3, padding=padding, activation='tanh', name='feature_conv1')

+    fconv2 = Conv1D(cond_size, 3, padding=padding, activation='tanh', name='feature_conv2')

     pembed = Embedding(256, 64, name='embed_pitch')

     cat_feat = Concatenate()([feat, Reshape((-1, 64))(pembed(pitch))])

     cfeat = fconv2(fconv1(cat_feat))

-    fdense1 = Dense(128, activation='tanh', name='feature_dense1')

-    fdense2 = Dense(128, activation='tanh', name='feature_dense2')

+    fdense1 = Dense(cond_size, activation='tanh', name='feature_dense1')

+    fdense2 = Dense(cond_size, activation='tanh', name='feature_dense2')

     if flag_e2e and quantize:

         fconv1.trainable = False

--- a/dnn/training_tf2/train_lpcnet.py

+++ b/dnn/training_tf2/train_lpcnet.py

@@ -45,6 +45,7 @@

 parser.add_argument('--grub-density-split', nargs=3, metavar=('<update>', '<reset>', '<state>'), type=float, help='density of each GRU B input gate (default 1.0, 1.0, 1.0)')

 parser.add_argument('--grua-size', metavar='<units>', default=384, type=int, help='number of units in GRU A (default 384)')

 parser.add_argument('--grub-size', metavar='<units>', default=16, type=int, help='number of units in GRU B (default 16)')

+parser.add_argument('--cond-size', metavar='<units>', default=128, type=int, help='number of units in conditioning network, aka frame rate network (default 128)')

 parser.add_argument('--epochs', metavar='<epochs>', default=120, type=int, help='number of epochs to train for (default 120)')

 parser.add_argument('--batch-size', metavar='<batch size>', default=128, type=int, help='batch size to use (default 128)')

 parser.add_argument('--end2end', dest='flag_e2e', action='store_true', help='Enable end-to-end training (with differentiable LPC computation')

@@ -121,7 +122,7 @@

 strategy = tf.distribute.experimental.MultiWorkerMirroredStrategy()

 with strategy.scope():

-    model, _, _ = lpcnet.new_lpcnet_model(rnn_units1=args.grua_size, rnn_units2=args.grub_size, batch_size=batch_size, training=True, quantize=quantize, flag_e2e = flag_e2e)

+    model, _, _ = lpcnet.new_lpcnet_model(rnn_units1=args.grua_size, rnn_units2=args.grub_size, batch_size=batch_size, training=True, quantize=quantize, flag_e2e = flag_e2e, cond_size=args.cond_size)

     if not flag_e2e:

         model.compile(optimizer=opt, loss='sparse_categorical_crossentropy', metrics='sparse_categorical_crossentropy')

     else:

-- 

⑨